MultiLoad-GAN: A GAN-Based Synthetic Load Group Generation Method Considering Spatial-Temporal Correlations

no code implementations • 3 Oct 2022 • Yi Hu, Yiyan Li, Lidong Song, Han Pyo Lee, PJ Rehm, Matthew Makdad, Edmond Miller, Ning Lu

This paper presents a deep-learning framework, Multi-load Generative Adversarial Network (MultiLoad-GAN), for generating a group of synthetic load profiles (SLPs) simultaneously.

Data Augmentation Generative Adversarial Network

A Novel Power-Band based Data Segmentation Method for Enhancing Meter Phase and Transformer-Meter Pairing Identification

no code implementations • 1 Oct 2022 • Han Pyo Lee, PJ Rehm, Matthew Makdad, Edmond Miller, Ning Lu

To ensure the credibility of the identification results, utility engineers conduct field verification for all 13 feeders.

A Novel Data Segmentation Method for Data-driven Phase Identification

no code implementations • 20 Nov 2021 • Han Pyo Lee, Mingzhi Zhang, Mesut Baran, Ning Lu, PJ Rehm, Edmond Miller, Matthew Makdad

To improve the identification accuracy, a data segmentation method is proposed to exclude data segments that are collected when the voltage correlation between smart meters on the same phase are weakened.

Clustering